Weaviate using tons of CPU during "tombstone_cleanup_begin"
Unfortunately, I see my weaviate container instance stuck at CPU intensive cycle for doing tombstone cleanup again, and this time it isnt due to shutdown corruption. I noted that this round, I have...
View ArticleDistance in meters when using within_geo_range
hi @jensenbox !! That’s interesting. I don’t believe it does I will poke internally about it and keep you posted. I have crafted a small test code for future reference:...
View ArticleHybrid similarity scoring is so weird - it doesn't make any sense
hi @A_S !! The best way to analyze this is with a working code so we can make sure we are at the same page. I was not able to reproduce the NAN issue. Can you provide some code for that? Here is some...
View ArticleEmbeded weaviate with objects stuck at 20; connect_to_local shows thousands...
Embedded will spawn a weaviate instance from the python client code. So a lot can happen there What you mean length of response?
View ArticleIssues facing while performing CRUD operations
That best thing here is to create some python code, if possible in pyv4, so we can try to reproduce the issue you are facing. Can you share a code for this? Thanks!
View ArticleDocker to K8s Backups using s3
well, if you don’t want to move your data, and is ok with actually mgirating it (copying from source and inserting to target), you can use this migration guide: weaviate.io Migrate data | Weaviate...
View ArticleUpdate existing chunks in a document with more than QUERY_MAXIMUM_RESULTS...
Hum. I see. Yeah, not sure this can be done differently from the suggested options
View ArticleEmbeded weaviate with objects stuck at 20; connect_to_local shows thousands...
collection = client.collections.get(class_name) response = collection.query.fetch_objects() object_cnts = len(response.objects) It shows 20 when I load first file; 15 when I upload 2nd file. After...
View ArticleUpdate existing chunks in a document with more than QUERY_MAXIMUM_RESULTS...
Sad, feels like a use-case other users might run into… If only the cursor API would allow for filtering everything would be golden. For now (and for other people reading this thread), we’ll probably...
View ArticleLocally running RAG pipeline with Verba and Llama3 with Ollama
I was able to get it to work, not the way I wanted but it works. I open weaviate db in a docker image, run ollama locally, and verba locally using the pip install goldenverba then verba start. Here’s...
View ArticleMax file size for pdf imports & Connection Interruption Error
I’m trying to upload a pdf to train the LLM. I’m using Weaviate in a docker-compose file, running verba and ollama3 locally. I’ve imported multiple pdfs already. I’m using a MacBook Pro running...
View ArticleProblem with near_text Query and Metadata Filtering in Weaviate
Weaviate Server Version: 1.27.0 Deployment Method: docker Multi Node? Number of Running Nodes: single node Client Language and Version: Client: 4.9.3, python Multitenancy?: no I’m encountering an...
View ArticleVectorization failed for some batches: 500, message='Internal Server Error'
Description 11.37 MB pdf file 647 chunks UI Error Response: Import for NASM's essentials of corrective exercise training ( PDFDrive ).pdf failed: Import for NASM's essentials of corrective exercise...
View Article[Docs] Python Dataclasses missing
Hey Duda, I suppose that is what I’m looking for. Where in that page did you link to this? It’s quite difficult to discover I would say. Also not easy to navigate to the reference you need when you...
View ArticleI am getting hnsw_vector_cache_prefill frequently
I have multiple cases and need help optimizing the code: Case 1: Suppose I have an additional property, "is_new", in the Book schema. Initially, is_new will be set to True when a book is added for the...
View Article[Docs] Python Dataclasses missing
It is linked from here: weaviate.io Python | Weaviate Utilize the Python client library to access Weaviate and streamline data processes. and also from the python client repo as well: GitHub GitHub -...
View ArticleVectorization failed for some batches: 500, message='Internal Server Error'
hi @bam ! This error seems to be coming from ollama. Can you get something from ollama logs?
View ArticleMax file size for pdf imports & Connection Interruption Error
hi @bam !! I believe those are related: Vectorization failed for some batches: 500, message='Internal Server Error'
View Article